I found that yolov8s_seg_engine has two outputs, output0 and output1，I converted the trained best.pt to onnx and then ran your v8trans.py, and then converted it to tensorrtr-accelerated best.engine through trtexec. The execution program showed an error.Is there any solution? Thank you so much
cils0014@cils0014-desktop:~/Desktop/aaa/yolov8_seg_tensorRT-master_v1$ ./build/yolov8_seg --yolov8 weights/yolov8s_seg.engine
[05/25/2024-18:25:06] [I] [TRT] Loaded engine size: 132 MiB
[05/25/2024-18:25:09] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +343, GPU +314, now: CPU 727, GPU 4890 (MiB)
[05/25/2024-18:25:09] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +130, now: CPU 0, GPU 130 (MiB)
Binding 0: images, size: 4915200, dims: (1, 3, 640, 640), type: 0
Binding 1: output0, size: 302400, dims: (1, 8400, 9), type: 0
[05/25/2024-18:25:09] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +0, now: CPU 727, GPU 4890 (MiB)
[05/25/2024-18:25:09] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +54, now: CPU 0, GPU 184 (MiB)
正在啟動 YOLOv8 物件檢測應用程序...
[ WARN:0] global /home/ubuntu/build_opencv/opencv/modules/videoio/src/cap_gstreamer.cpp (1100) open OpenCV | GStreamer warning: Cannot query video position: status=0, value=-1, duration=-1
USB 相機已成功打開，正在初始化 YOLOv8 模型...
讀取相機幀的線程已啟動
物件檢測的線程已啟動
FPS: 51.3383
[05/25/2024-18:25:13] [E] [TRT] 3: Cannot find binding of given name: output1
CUDA error 1 at /home/cils0014/Desktop/aaa/yolov8_seg_tensorRT-master_v1/src/utils/postprocess.cu:324yolov8_seg: /home/cils0014/Desktop/aaa/yolov8_seg_tensorRT-master_v1/src/utils/postprocess.cu:324: yolo::BoxArray post_process(float, float, memory_ctrl::Memory&, AffineMatrix&, float, float, int, int, int): Assertion `0' failed.
I found that yolov8s_seg_engine has two outputs, output0 and output1，I converted the trained best.pt to onnx and then ran your v8trans.py, and then converted it to tensorrtr-accelerated best.engine through trtexec. The execution program showed an error.Is there any solution? Thank you so much
cils0014@cils0014-desktop:~/Desktop/aaa/yolov8_seg_tensorRT-master_v1$ ./build/yolov8_seg --yolov8 weights/yolov8s_seg.engine [05/25/2024-18:25:06] [I] [TRT] Loaded engine size: 132 MiB [05/25/2024-18:25:09] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +343, GPU +314, now: CPU 727, GPU 4890 (MiB) [05/25/2024-18:25:09] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in engine deserialization: CPU +0, GPU +130, now: CPU 0, GPU 130 (MiB) Binding 0: images, size: 4915200, dims: (1, 3, 640, 640), type: 0 Binding 1: output0, size: 302400, dims: (1, 8400, 9), type: 0 [05/25/2024-18:25:09] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +0, GPU +0, now: CPU 727, GPU 4890 (MiB) [05/25/2024-18:25:09] [I] [TRT] [MemUsageChange] TensorRT-managed allocation in IExecutionContext creation: CPU +0, GPU +54, now: CPU 0, GPU 184 (MiB) 正在啟動 YOLOv8 物件檢測應用程序... [ WARN:0] global /home/ubuntu/build_opencv/opencv/modules/videoio/src/cap_gstreamer.cpp (1100) open OpenCV | GStreamer warning: Cannot query video position: status=0, value=-1, duration=-1 USB 相機已成功打開，正在初始化 YOLOv8 模型... 讀取相機幀的線程已啟動 物件檢測的線程已啟動 FPS: 51.3383 [05/25/2024-18:25:13] [E] [TRT] 3: Cannot find binding of given name: output1 CUDA error 1 at /home/cils0014/Desktop/aaa/yolov8_seg_tensorRT-master_v1/src/utils/postprocess.cu:324yolov8_seg: /home/cils0014/Desktop/aaa/yolov8_seg_tensorRT-master_v1/src/utils/postprocess.cu:324: yolo::BoxArray post_process(float, float, memory_ctrl::Memory&, AffineMatrix&, float, float, int, int, int): Assertion `0' failed.